Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.9560. Min Act: -0.1700

Data Index: 275598 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.9872. Min Act: -0.1700

Data Index: 846119 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.8622. Min Act: -0.1700

Data Index: 296734 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7060. Min Act: -0.1700

Data Index: 581361 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7997. Min Act: -0.1700

Data Index: 9996 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7060. Min Act: -0.1700

Data Index: 365965 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.6122. Min Act: -0.1700

Data Index: 1303781 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7372. Min Act: -0.1700

Data Index: 1117516 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7372. Min Act: -0.1700

Data Index: 161418 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7685. Min Act: -0.1700

Data Index: 264103 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7685. Min Act: -0.1700

Data Index: 672034 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7372. Min Act: -0.1700

Data Index: 292159 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.6747. Min Act: -0.1700

Data Index: 21854 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7997. Min Act: -0.1700

Data Index: 890083 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7685. Min Act: -0.1700

Data Index: 814149 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.7060. Min Act: -0.1700

Data Index: 666265 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.6747. Min Act: -0.1700

Data Index: 256390 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.6747. Min Act: -0.1700

Data Index: 416302 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.6747. Min Act: -0.1700

Data Index: 51707 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 5.9872. Min Range: -5.9872

Max Act: 5.5810. Min Act: -0.1700

Data Index: 692959 (C4 (Web Text))

Max Activating Token Index: 390